• DocumentCode
    873722
  • Title

    Managing locality sets: the model and fixed-size buffers

  • Author

    Choi, Andrew ; Ruschitzka, Manfred

  • Author_Institution
    Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
  • Volume
    42
  • Issue
    2
  • fYear
    1993
  • fDate
    2/1/1993 12:00:00 AM
  • Firstpage
    190
  • Lastpage
    204
  • Abstract
    A memory-management model based on describing reference behavior in terms of locality-set sequences is proposed. Specialized for fixed-size buffers, this model is used to define the PSETMIN and SETMIN strategies which are proven to minimize the number of page faults in the presence and absence of prepaging, respectively. In contrast to MIN, they are also realizable for certain computations. The methodology for obtaining the locality-set sequence of a computation in advance is illustrated for relational database management systems with multiattribute-index catalogs, and the concomitant performance gains are discussed. In general, for applications that maintain their own organized collections of data, optimal locality-set management of individual computations provides an alternative to the widely used general-purpose strategies based on heuristics
  • Keywords
    relational databases; storage management; MIN; PSETMIN; SETMIN strategies; concomitant performance gains; fixed-size buffers; heuristics; locality-set sequences; memory-management model; multiattribute-index catalogs; optimal locality-set management; page faults; prepaging; reference behavior; relational database management systems; Catalogs; Computational efficiency; Computational modeling; Computer science; Extraterrestrial measurements; Memory management; Performance gain; Physics computing; Relational databases;
  • fLanguage
    English
  • Journal_Title
    Computers, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9340
  • Type

    jour

  • DOI
    10.1109/12.204792
  • Filename
    204792